KR20180084580A - Device and method to generate abstractive summaries from large multi-paragraph texts, recording medium for performing the method - Google Patents

Device and method to generate abstractive summaries from large multi-paragraph texts, recording medium for performing the method Download PDF

Info

Publication number
KR20180084580A
KR20180084580A KR1020170030546A KR20170030546A KR20180084580A KR 20180084580 A KR20180084580 A KR 20180084580A KR 1020170030546 A KR1020170030546 A KR 1020170030546A KR 20170030546 A KR20170030546 A KR 20170030546A KR 20180084580 A KR20180084580 A KR 20180084580A
Authority
KR
South Korea
Prior art keywords
abstract
unit
internal representation
output
paragraph
Prior art date
Application number
KR1020170030546A
Other languages
Korean (ko)
Other versions
KR101882906B1 (en
Inventor
이민호
데니스사이 모이랑뎀
Original Assignee
경북대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 경북대학교 산학협력단 filed Critical 경북대학교 산학협력단
Priority to PCT/KR2017/011747 priority Critical patent/WO2018135723A1/en
Publication of KR20180084580A publication Critical patent/KR20180084580A/en
Application granted granted Critical
Publication of KR101882906B1 publication Critical patent/KR101882906B1/en

Links

Classifications

    • G06F17/2705—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/205—Parsing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent

Abstract

A device for creating an abstract of multi-paragraph texts includes: an input unit for automatically dividing a document into paragraphs and transmitting the same; an encoding unit for transforming the paragraphs received from the input unit into an internal representation vector, generating, as an internal representation, a vector transformed through a recurrent neural network (RNN) including a multiple timescales grated recurrent unit (MTGRU) having multiple constants, and transmitting the internal representation; a decoding unit for decoding the internal representation received from the encoding unit through the RNN including the MTGRU and generating sentences by using linguistic modeling; and an output unit for collecting an abstract output of each paragraph to output the final abstract. Accordingly, an abstract expression is generated so that an abstract more similar to a man-made abstract can be created.
KR1020170030546A 2017-01-17 2017-03-10 Device and method to generate abstractive summaries from large multi-paragraph texts, recording medium for performing the method KR101882906B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/KR2017/011747 WO2018135723A1 (en) 2017-01-17 2017-10-24 Device and method for generating abstract summary of multiple-paragraph text, and recording medium for performing same method

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020170007888 2017-01-17
KR20170007888 2017-01-17

Publications (2)

Publication Number Publication Date
KR20180084580A true KR20180084580A (en) 2018-07-25
KR101882906B1 KR101882906B1 (en) 2018-07-27

Family

ID=63059102

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020170030546A KR101882906B1 (en) 2017-01-17 2017-03-10 Device and method to generate abstractive summaries from large multi-paragraph texts, recording medium for performing the method

Country Status (1)

Country Link
KR (1) KR101882906B1 (en)

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109635103A (en) * 2018-12-17 2019-04-16 北京百度网讯科技有限公司 Abstraction generating method and device
CN110147532A (en) * 2019-01-24 2019-08-20 腾讯科技（深圳）有限公司 Coding method, device, equipment and storage medium
CN110389820A (en) * 2019-06-28 2019-10-29 浙江大学 A kind of private clound method for scheduling task carrying out resources based on v-TGRU model
CN111026861A (en) * 2019-12-10 2020-04-17 腾讯科技（深圳）有限公司 Text abstract generation method, text abstract training method, text abstract generation device, text abstract training device, text abstract equipment and text abstract training medium
KR20210125275A (en) * 2020-04-08 2021-10-18 에스케이 주식회사 Deep Learning based Document Summarization Method and System
CN113704457A (en) * 2021-07-23 2021-11-26 北京搜狗科技发展有限公司 Abstract generation method and device and storage medium
CN113743082A (en) * 2021-09-16 2021-12-03 京东科技信息技术有限公司 Data processing method, system, storage medium and electronic equipment
KR20220091035A (en) * 2020-12-23 2022-06-30 주식회사 카카오 Summary evaluation device, control method thereof and summary evaluation program
CN115982343A (en) * 2023-03-13 2023-04-18 阿里巴巴达摩院(杭州)科技有限公司 Abstract generation method, method and device for training abstract generation model

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100785927B1 (en) 2006-06-02 2007-12-17 삼성전자주식회사 Method and apparatus for providing data summarization
KR20130116908A (en) 2011-01-28 2013-10-24 인텔 코포레이션 Methods and systems to summarize a source text as a function of contextual information
KR20170107015A (en) * 2015-11-25 2017-09-22 바이두 유에스에이 엘엘씨 End-to-end speech recognition

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100785927B1 (en) 2006-06-02 2007-12-17 삼성전자주식회사 Method and apparatus for providing data summarization
KR20130116908A (en) 2011-01-28 2013-10-24 인텔 코포레이션 Methods and systems to summarize a source text as a function of contextual information
KR20170107015A (en) * 2015-11-25 2017-09-22 바이두 유에스에이 엘엘씨 End-to-end speech recognition

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
A.M.Rush et. al., A neural attention model for sentence summarization, Proc. of 2015 conference EMNLP, pp.379-389, 2015. *
Minsoo Kim, Moirangthem Dennis Singh, and Minho Lee, "Towards Abstraction from Extraction: Multiple Timescale Gated Recurrent Unit for Summarization", Association for Computational Linguistics (2016).
R. Nallapati et al., Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond, Proc. of 20th SIGNLL Conference, pp.280-290, 2016.08.07 *
S. Chopra et al., Abstractive Sentence Summarization with Attentive Recurrent Neural Networks, Proc. of NAACL-HLT 2016, pp.93-98, 2016.06 *
권영대 외, 문장 수반 관계 추론을 통한 문서 요약, 한국정보과학회 학술발표 논문집, pp.711-713, 2016.06 *

Cited By (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109635103A (en) * 2018-12-17 2019-04-16 北京百度网讯科技有限公司 Abstraction generating method and device
CN109635103B (en) * 2018-12-17 2022-05-20 北京百度网讯科技有限公司 Abstract generation method and device
CN110147532B (en) * 2019-01-24 2023-08-25 腾讯科技（深圳）有限公司 Encoding method, apparatus, device and storage medium
CN110147532A (en) * 2019-01-24 2019-08-20 腾讯科技（深圳）有限公司 Coding method, device, equipment and storage medium
CN110389820A (en) * 2019-06-28 2019-10-29 浙江大学 A kind of private clound method for scheduling task carrying out resources based on v-TGRU model
CN111026861A (en) * 2019-12-10 2020-04-17 腾讯科技（深圳）有限公司 Text abstract generation method, text abstract training method, text abstract generation device, text abstract training device, text abstract equipment and text abstract training medium
CN111026861B (en) * 2019-12-10 2023-07-04 腾讯科技（深圳）有限公司 Text abstract generation method, training device, training equipment and medium
KR20210125275A (en) * 2020-04-08 2021-10-18 에스케이 주식회사 Deep Learning based Document Summarization Method and System
KR20220091035A (en) * 2020-12-23 2022-06-30 주식회사 카카오 Summary evaluation device, control method thereof and summary evaluation program
CN113704457A (en) * 2021-07-23 2021-11-26 北京搜狗科技发展有限公司 Abstract generation method and device and storage medium
CN113704457B (en) * 2021-07-23 2024-03-01 北京搜狗科技发展有限公司 Method and device for generating abstract and storage medium
CN113743082A (en) * 2021-09-16 2021-12-03 京东科技信息技术有限公司 Data processing method, system, storage medium and electronic equipment
CN113743082B (en) * 2021-09-16 2024-04-05 京东科技信息技术有限公司 Data processing method, system, storage medium and electronic equipment
CN115982343B (en) * 2023-03-13 2023-08-22 阿里巴巴达摩院(杭州)科技有限公司 Abstract generation method, and method and device for training abstract generation model
CN115982343A (en) * 2023-03-13 2023-04-18 阿里巴巴达摩院(杭州)科技有限公司 Abstract generation method, method and device for training abstract generation model

Also Published As

Publication number Publication date
KR101882906B1 (en) 2018-07-27

Similar Documents

Publication Publication Date Title
KR20180084580A (en) Device and method to generate abstractive summaries from large multi-paragraph texts, recording medium for performing the method
MX2017013899A (en) Method and system for automatically generating functional architecture documents and documents for software design and analysis specification.
AU2016331881A8 (en) Q-compensated full wavefield inversion
MX2016013015A (en) Methods and systems of handling a dialog with a robot.
WO2014140977A9 (en) Improving entity recognition in natural language processing systems
WO2008106664A3 (en) Human behavioral modeling and simulation framework
WO2018212584A3 (en) Method and apparatus for classifying class, to which sentence belongs, using deep neural network
EP3789928A3 (en) Neural network method and apparatus
Krischer et al. Generating seismograms with deep neural networks
De Sousa Webber Semantic folding theory and its application in semantic fingerprinting
FI20196098A1 (en) Neural network based solution
Thanh Nguyen et al. A robust 3d-2d interactive tool for scene segmentation and annotation
Zizhuang Wang et al. Riemannian Normalizing Flow on Variational Wasserstein Autoencoder for Text Modeling
Hummels et al. Trident: Synthetic spectrum generator
LaChapelle Functional Integration on Topological Groups II: Functional Mellin Transforms
Shih-Han Wang et al. Toward Few-step Adversarial Training from a Frequency Perspective
Kobayashi et al. Improving user experiences in talking to robots using ASE-based backchannel feedbacks
Quyen Pham et al. A Noise-Robust Method with Smoothed\ell_1/\ell_2 Regularization for Sparse Moving-Source Mapping
Rafae Khan et al. Diversity by Phonetics and its Application in Neural Machine Translation
Ferreira Luz et al. Semantic Parsing Natural Language into SPARQL: Improving Target Language Representation with Neural Attention
Zenocratti et al. Caracterización de galaxias elípticas en contexto cosmológico
Capelas de Oliveira et al. Analytic components for the hadronic total cross-section: Fractional calculus and Mellin transform
De Bortoli Fávero et al. BERT_SE: A Pre-trained Language Representation Model for Software Engineering
Bastiaan Kleijn et al. Wavenet based low rate speech coding
Indra Winata et al. Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer

Legal Events

Date Code Title Description
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant